BMW Hackathon

OPENS AT: Nov 14, 12:30 PM

CLOSES AT: Dec 12, 01:25 PM

DURATION: 28 days 55m

BMW SORDI.ai Hackathon 2022

Online 533 Participating LIVE

Discussions

Social Share

Invite friends via email

ABOUT CHALLENGE

Overview

The SORDI.ai Hackathon 2022 for Industrial Object Detection Challenge invites brilliant minds passionate about artificial intelligence (AI) and machine learning (ML) to tackle real AI-based computer vision (CV) challenges and help build object detection and recognition solutions based on BMW Group’s largest synthetic object dataset for industries.

In today's world, ML and CV have gained unprecedented interest, with extensive research in academia and increasing implementation in industry. Object detection, a subset of CV, provides computers with the ability to perceive the word visually, and mimics human vision to detect and identify salient objects in an image or a video. One major challenge is the need to train and deploy different object detection models for specific industrial use cases. This in turn requires a significant amount of high-quality training data which is oftentimes unavailable, especially in industrial domains due to confidentiality, scene setup, and many more considerations. To overcome this issue, BMW Group, in collaboration with its partners NVIDIA, Microsoft, Idealworks, Inmind.ai, and many prestigious universities from around the globe, created SORDI (i.e., Synthetic Object Recognition Dataset for Industries): the largest and most extensive collection of synthetic visual industrial assets (e.g., pallets, boxes, cardboard, bolts, etc.). SORDI can be used to enhance CV tasks in digital-twin environments (e.g., a simulated factory floor) as well as their real-world counterparts.

This contest aims at utilizing and popularizing the SORDI dataset for industrial object detection and recognition. Your task in this hackathon is to train object detection models based on subsets from SORDI to achieve top accuracy levels for real-world BMW use cases.

Challenge yourself, put your machine learning and computer vision skills to the test, try out new things, and learn in the process!

Awards

 


 

Important Dates

Registration starts: October 24th, 2022 

Start of Stage 1: November 14th, 2022 --- End of Stage 1: December 12th, 2022

Qualifiers announcements: December 19th, 2022

Start of Stage 2: January 16th, 2023 --- End of Stage 2: February 13th, 2023

Winners’ announcements: March 6th, 2023

Download the Problem Statement

Visit: SORDI.ai/hackathon


Eligibility

Anyone, who is not BMW Group, Microsoft, or NVIDIA staff, or intern can participate in this hackathon. You can have any qualifications, be a working professional, freelancer, or on a career break, a student of any college, or citizen of any country, with the exception of restricted jurisdictions (any place declared an embargoed or restricted destination by Trade Controls Laws; currently those places include Cuba, Iran, Italy, North Korea, Philippines, Sudan, Syria, Region of Crimea, Russia). All participants must be at least 18 years old when entering the hackathon.

 


Partners

 

ABOUT COMPANY

SORDI contains hundreds of thousands of photo-realistic images for 80+ distinct object classes highlighting logistics, transportation, signage, tools, and office assets. They are path-trace rendered in NVIDIA Omniverse using the latest RTX technology and Pixar’s USD pipeline. SORDI significantly simplifies training CV models to recognize equipment in numerous factory environments. Published by BMW Group, SORDI helps developers and researchers to streamline and accelerate the training of artificial intelligence in production. Together with Microsoft, NVIDIA, and idealworks, SORDI has been made available as open-source, to build the world’s largest reference dataset for artificial intelligence in the field of manufacturing. For more details, please see https://www.sordi.ai.

GUIDELINES

  • Stage 1: The submissions will be evaluated in real-time. The evaluation criteria is based on the Accuracy and the Mean Average Precision at an Intersection over Union equa...
more

FAQs

What is this hackathon about?

The hackathon consists of recognizing and detecting main industrial assets using a subset of the SORDI.ai dataset. For more information, SORDI...

more
Notifications
View All Notifications

?